@ai-sdk/amazon-bedrock 5.0.0-beta.8 → 5.0.0-beta.85

package/docs/08-amazon-bedrock.mdx

@@ -35,6 +35,31 @@ See the [Model Access Docs](https://docs.aws.amazon.com/bedrock/latest/userguide
 
 ### Authentication
 
+The Amazon Bedrock provider supports two authentication methods with automatic fallback: API key authentication (recommended) and AWS SigV4 authentication using IAM credentials or the AWS SDK credentials chain.
+
+#### Using an API Key (Recommended)
+
+API key authentication provides a simpler setup compared to AWS SigV4 authentication. When an API key is supplied, it takes precedence over any SigV4 credentials.
+
+Generate a bedrock API key from the [AWS console](https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html), then either set it as the `AWS_BEARER_TOKEN_BEDROCK` environment variable:
+
+```bash
+AWS_BEARER_TOKEN_BEDROCK=your-api-key-here
+```
+
+or pass it directly to `createAmazonBedrock`:
+
+```ts
+import { createAmazonBedrock } from '@ai-sdk/amazon-bedrock';
+
+const amazonBedrock = createAmazonBedrock({
+  apiKey: 'your-api-key-here',
+  region: 'us-east-1',
+});
+```
+
+When `apiKey` is omitted, the provider falls back to `AWS_BEARER_TOKEN_BEDROCK`, and then to SigV4 authentication if neither is set.
+
 #### Using IAM Access Key and Secret Key
 
 **Step 1: Creating AWS Access Key and Secret Key**
@@ -105,7 +130,7 @@ _Usage:_
 import { createAmazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { fromNodeProviderChain } from '@aws-sdk/credential-providers';
 
-const bedrock = createAmazonBedrock({
+const amazonBedrock = createAmazonBedrock({
   region: 'us-east-1',
   credentialProvider: fromNodeProviderChain(),
 });
@@ -113,10 +138,10 @@ const bedrock = createAmazonBedrock({
 
 ## Provider Instance
 
-You can import the default provider instance `bedrock` from `@ai-sdk/amazon-bedrock`:
+You can import the default provider instance `amazonBedrock` from `@ai-sdk/amazon-bedrock`:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 ```
 
 If you need a customized setup, you can import `createAmazonBedrock` from `@ai-sdk/amazon-bedrock` and create a provider instance with your settings:
@@ -124,7 +149,7 @@ If you need a customized setup, you can import `createAmazonBedrock` from `@ai-s
 ```ts
 import { createAmazonBedrock } from '@ai-sdk/amazon-bedrock';
 
-const bedrock = createAmazonBedrock({
+const amazonBedrock = createAmazonBedrock({
   region: 'us-east-1',
   accessKeyId: 'xxxxxxxxx',
   secretAccessKey: 'xxxxxxxxx',
@@ -133,12 +158,10 @@ const bedrock = createAmazonBedrock({
 ```
 
 <Note>
-  The credentials settings fall back to environment variable defaults described
-  below. These may be set by your serverless environment without your awareness,
-  which can lead to merged/conflicting credential values and provider errors
-  around failed authentication. If you're experiencing issues be sure you are
-  explicitly specifying all settings (even if `undefined`) to avoid any
-  defaults.
+  Omitted options use the environment variables below. When **both**
+  `accessKeyId` and `secretAccessKey` are strings, SigV4 uses a **`sessionToken`
+  only if you pass one** - not `AWS_SESSION_TOKEN` from the environment - so
+  static keys are not mixed with workload tokens (e.g. EKS IRSA).
 </Note>
 
 You can use the following optional settings to customize the Amazon Bedrock provider instance:
@@ -160,8 +183,10 @@ You can use the following optional settings to customize the Amazon Bedrock prov
 
 - **sessionToken** _string_
 
-  Optional. The AWS session token that you want to use for the API calls.
-  It uses the `AWS_SESSION_TOKEN` environment variable by default.
+  Optional. For temporary credentials. With **both** access keys set as strings,
+  pass the token here if needed; `AWS_SESSION_TOKEN` from the environment is not
+  used. If either key is taken from the environment, omitting `sessionToken`
+  allows `AWS_SESSION_TOKEN`.
 
 - **credentialProvider** _() =&gt; Promise&lt;&#123; accessKeyId: string; secretAccessKey: string; sessionToken?: string; &#125;&gt;_
 
@@ -195,14 +220,14 @@ You can create models that call the Bedrock API using the provider instance.
 The first argument is the model id, e.g. `meta.llama3-70b-instruct-v1:0`.
 
 ```ts
-const model = bedrock('meta.llama3-70b-instruct-v1:0');
+const model = amazonBedrock('meta.llama3-70b-instruct-v1:0');
 ```
 
 Amazon Bedrock models also support some model specific provider options that are not part of the [standard call settings](/docs/ai-sdk-core/settings).
 You can pass them in the `providerOptions` argument:
 
 ```ts
-const model = bedrock('anthropic.claude-3-sonnet-20240229-v1:0');
+const model = amazonBedrock('anthropic.claude-3-sonnet-20240229-v1:0');
 
 await generateText({
   model,
@@ -219,11 +244,11 @@ Documentation for additional settings based on the selected model can be found w
 You can use Amazon Bedrock language models to generate text with the `generateText` function:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 const { text } = await generateText({
-  model: bedrock('meta.llama3-70b-instruct-v1:0'),
+  model: amazonBedrock('meta.llama3-70b-instruct-v1:0'),
   prompt: 'Write a vegetarian lasagna recipe for 4 people.',
 });
 ```
@@ -241,11 +266,11 @@ Amazon Bedrock language models can also be used in the `streamText` function
 The Amazon Bedrock provider supports file inputs, e.g. PDF files.
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 const result = await generateText({
-  model: bedrock('anthropic.claude-3-haiku-20240307-v1:0'),
+  model: amazonBedrock('anthropic.claude-3-haiku-20240307-v1:0'),
   messages: [
     {
       role: 'user',
@@ -267,10 +292,10 @@ const result = await generateText({
 You can use the `bedrock` provider options to utilize [Amazon Bedrock Guardrails](https://aws.amazon.com/bedrock/guardrails/):
 
 ```ts
-import { type AmazonBedrockLanguageModelOptions } from '@ai-sdk/amazon-bedrock';
+import { type AmazonBedrockLanguageModelChatOptions } from '@ai-sdk/amazon-bedrock';
 
 const result = await generateText({
-  model: bedrock('anthropic.claude-3-sonnet-20240229-v1:0'),
+  model: amazonBedrock('anthropic.claude-3-sonnet-20240229-v1:0'),
   prompt: 'Write a story about space exploration.',
   providerOptions: {
     bedrock: {
@@ -280,7 +305,7 @@ const result = await generateText({
         trace: 'enabled' as const,
         streamProcessingMode: 'async',
       },
-    } satisfies AmazonBedrockLanguageModelOptions,
+    } satisfies AmazonBedrockLanguageModelChatOptions,
   },
 });
 ```
@@ -303,13 +328,13 @@ Amazon Bedrock supports citations for document-based inputs across compatible mo
 - Models can cite specific parts of documents you provide, making it easier to trace information back to its source (Not Supported Yet)
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateText, Output } from 'ai';
 import { z } from 'zod';
 import fs from 'fs';
 
 const result = await generateText({
-  model: bedrock('apac.anthropic.claude-sonnet-4-20250514-v1:0'),
+  model: amazonBedrock('apac.anthropic.claude-sonnet-4-20250514-v1:0'),
   output: Output.object({
     schema: z.object({
       summary: z.string().describe('Summary of the PDF document'),
@@ -377,14 +402,14 @@ Cache usage information is returned in the `providerMetadata` object. See exampl
 </Note>
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 const cyberpunkAnalysis =
   '... literary analysis of cyberpunk themes and concepts ...';
 
 const result = await generateText({
-  model: bedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
+  model: amazonBedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
   messages: [
     {
       role: 'system',
@@ -413,14 +438,14 @@ console.log(result.providerMetadata?.bedrock?.usage);
 Cache points also work with streaming responses:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { streamText } from 'ai';
 
 const cyberpunkAnalysis =
   '... literary analysis of cyberpunk themes and concepts ...';
 
 const result = streamText({
-  model: bedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
+  model: amazonBedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
   messages: [
     {
       role: 'assistant',
@@ -477,19 +502,19 @@ Amazon Bedrock supports model creator-specific reasoning features:
 
 ```ts
 import {
-  bedrock,
-  type AmazonBedrockLanguageModelOptions,
+  amazonBedrock,
+  type AmazonBedrockLanguageModelChatOptions,
 } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 // Anthropic example
 const anthropicResult = await generateText({
-  model: bedrock('us.anthropic.claude-sonnet-4-5-20250929-v1:0'),
+  model: amazonBedrock('us.anthropic.claude-sonnet-4-5-20250929-v1:0'),
   prompt: 'How many people will live in the world in 2040?',
   providerOptions: {
     bedrock: {
       reasoningConfig: { type: 'enabled', budgetTokens: 1024 },
-    } satisfies AmazonBedrockLanguageModelOptions,
+    } satisfies AmazonBedrockLanguageModelChatOptions,
   },
 });
 
@@ -498,12 +523,12 @@ console.log(anthropicResult.text); // text response
 
 // Nova 2 example
 const amazonResult = await generateText({
-  model: bedrock('us.amazon.nova-2-lite-v1:0'),
+  model: amazonBedrock('us.amazon.nova-2-lite-v1:0'),
   prompt: 'How many people will live in the world in 2040?',
   providerOptions: {
     bedrock: {
       reasoningConfig: { type: 'enabled', maxReasoningEffort: 'medium' },
-    } satisfies AmazonBedrockLanguageModelOptions,
+    } satisfies AmazonBedrockLanguageModelChatOptions,
   },
 });
 
@@ -514,24 +539,55 @@ console.log(amazonResult.text); // text response
 See [AI SDK UI: Chatbot](/docs/ai-sdk-ui/chatbot#reasoning) for more details
 on how to integrate reasoning into your chatbot.
 
+## Service Tiers
+
+Amazon Bedrock supports selecting an inference service tier per request via the `serviceTier` provider option.
+
+```ts
+import {
+  amazonBedrock,
+  type AmazonBedrockLanguageModelChatOptions,
+} from '@ai-sdk/amazon-bedrock';
+import { generateText } from 'ai';
+
+const result = await generateText({
+  model: amazonBedrock('us.anthropic.claude-sonnet-4-20250514-v1:0'),
+  prompt: 'Summarize this support ticket backlog.',
+  providerOptions: {
+    bedrock: {
+      serviceTier: 'priority',
+    } satisfies AmazonBedrockLanguageModelChatOptions,
+  },
+});
+```
+
+Supported values are:
+
+- `reserved`
+- `priority`
+- `default`
+- `flex`
+
+See the [Amazon Bedrock service tiers documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/service-tiers-inference.html) for model availability and behavior.
+
 ## Extended Context Window
 
 Claude Sonnet 4 models on Amazon Bedrock support an extended context window of up to 1 million tokens when using the `context-1m-2025-08-07` beta feature.
 
 ```ts
 import {
-  bedrock,
-  type AmazonBedrockLanguageModelOptions,
+  amazonBedrock,
+  type AmazonBedrockLanguageModelChatOptions,
 } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 const result = await generateText({
-  model: bedrock('us.anthropic.claude-sonnet-4-20250514-v1:0'),
+  model: amazonBedrock('us.anthropic.claude-sonnet-4-20250514-v1:0'),
   prompt: 'analyze this large document...',
   providerOptions: {
     bedrock: {
       anthropicBeta: ['context-1m-2025-08-07'],
-    } satisfies AmazonBedrockLanguageModelOptions,
+    } satisfies AmazonBedrockLanguageModelChatOptions,
   },
 });
 ```
@@ -556,7 +612,7 @@ They are available via the `tools` property of the provider instance.
 The Bash Tool allows running bash commands. Here's how to create and use it:
 
 ```ts
-const bashTool = bedrock.tools.bash_20241022({
+const bashTool = amazonBedrock.tools.bash_20241022({
   execute: async ({ command, restart }) => {
     // Implement your bash command execution logic here
     // Return the result of the command execution
@@ -576,7 +632,7 @@ The Text Editor Tool provides functionality for viewing and editing text files.
 **For Claude 4 models (Opus & Sonnet):**
 
 ```ts
-const textEditorTool = bedrock.tools.textEditor_20250429({
+const textEditorTool = amazonBedrock.tools.textEditor_20250429({
   execute: async ({
     command,
     path,
@@ -596,7 +652,7 @@ const textEditorTool = bedrock.tools.textEditor_20250429({
 **For Claude 3.5 Sonnet and earlier models:**
 
 ```ts
-const textEditorTool = bedrock.tools.textEditor_20241022({
+const textEditorTool = amazonBedrock.tools.textEditor_20241022({
   execute: async ({
     command,
     path,
@@ -632,7 +688,7 @@ When using the Text Editor Tool, make sure to name the key in the tools object c
 ```ts
 // For Claude 4 models
 const response = await generateText({
-  model: bedrock('us.anthropic.claude-sonnet-4-20250514-v1:0'),
+  model: amazonBedrock('us.anthropic.claude-sonnet-4-20250514-v1:0'),
   prompt:
     "Create a new file called example.txt, write 'Hello World' to it, and run 'cat example.txt' in the terminal",
   tools: {
@@ -642,7 +698,7 @@ const response = await generateText({
 
 // For Claude 3.5 Sonnet and earlier
 const response = await generateText({
-  model: bedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
+  model: amazonBedrock('anthropic.claude-3-5-sonnet-20241022-v2:0'),
   prompt:
     "Create a new file called example.txt, write 'Hello World' to it, and run 'cat example.txt' in the terminal",
   tools: {
@@ -656,7 +712,7 @@ const response = await generateText({
 The Computer Tool enables control of keyboard and mouse actions on a computer:
 
 ```ts
-const computerTool = bedrock.tools.computer_20241022({
+const computerTool = amazonBedrock.tools.computer_20241022({
   displayWidthPx: 1920,
   displayHeightPx: 1080,
   displayNumber: 0, // Optional, for X11 environments
@@ -689,7 +745,7 @@ const computerTool = bedrock.tools.computer_20241022({
   toModelOutput({ output }) {
     return typeof output === 'string'
       ? [{ type: 'text', text: output }]
-      : [{ type: 'image', data: output.data, mediaType: 'image/png' }];
+      : [{ type: 'file-data', data: output.data, mediaType: 'image/png' }];
   },
 });
 ```
@@ -779,18 +835,18 @@ You can create models that call the Bedrock API [Bedrock API](https://docs.aws.a
 using the `.embedding()` factory method.
 
 ```ts
-const model = bedrock.embedding('amazon.titan-embed-text-v1');
+const model = amazonBedrock.embedding('amazon.titan-embed-text-v1');
 ```
 
 Bedrock Titan embedding model amazon.titan-embed-text-v2:0 supports several additional settings.
 You can pass them as an options argument:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { type AmazonBedrockEmbeddingModelOptions } from '@ai-sdk/amazon-bedrock';
 import { embed } from 'ai';
 
-const model = bedrock.embedding('amazon.titan-embed-text-v2:0');
+const model = amazonBedrock.embedding('amazon.titan-embed-text-v2:0');
 
 const { embedding } = await embed({
   model,
@@ -819,12 +875,12 @@ The following optional provider options are available for Bedrock Titan embeddin
 Amazon Nova embedding models support additional provider options:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { type AmazonBedrockEmbeddingModelOptions } from '@ai-sdk/amazon-bedrock';
 import { embed } from 'ai';
 
 const { embedding } = await embed({
-  model: bedrock.embedding('amazon.nova-embed-text-v2:0'),
+  model: amazonBedrock.embedding('amazon.nova-embed-text-v2:0'),
   value: 'sunny day at the beach',
   providerOptions: {
     bedrock: {
@@ -855,12 +911,12 @@ The following optional provider options are available for Nova embedding models:
 Cohere embedding models on Bedrock require an `inputType` and support truncation:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { type AmazonBedrockEmbeddingModelOptions } from '@ai-sdk/amazon-bedrock';
 import { embed } from 'ai';
 
 const { embedding } = await embed({
-  model: bedrock.embedding('cohere.embed-english-v3'),
+  model: amazonBedrock.embedding('cohere.embed-english-v3'),
   value: 'sunny day at the beach',
   providerOptions: {
     bedrock: {
@@ -897,13 +953,13 @@ You can create models that call the [Bedrock Rerank API](https://docs.aws.amazon
 using the `.reranking()` factory method.
 
 ```ts
-const model = bedrock.reranking('cohere.rerank-v3-5:0');
+const model = amazonBedrock.reranking('cohere.rerank-v3-5:0');
 ```
 
 You can use Amazon Bedrock reranking models to rerank documents with the `rerank` function:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { rerank } from 'ai';
 
 const documents = [
@@ -913,7 +969,7 @@ const documents = [
 ];
 
 const { ranking } = await rerank({
-  model: bedrock.reranking('cohere.rerank-v3-5:0'),
+  model: amazonBedrock.reranking('cohere.rerank-v3-5:0'),
   documents,
   query: 'talk about rain',
   topN: 2,
@@ -929,11 +985,11 @@ console.log(ranking);
 Amazon Bedrock reranking models support additional provider options that can be passed via `providerOptions.bedrock`:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { rerank } from 'ai';
 
 const { ranking } = await rerank({
-  model: bedrock.reranking('cohere.rerank-v3-5:0'),
+  model: amazonBedrock.reranking('cohere.rerank-v3-5:0'),
   documents: ['sunny day at the beach', 'rainy afternoon in the city'],
   query: 'talk about rain',
   providerOptions: {
@@ -975,17 +1031,17 @@ Overview](https://docs.aws.amazon.com/ai/responsible-ai/nova-canvas/overview.htm
 </Note>
 
 ```ts
-const model = bedrock.image('amazon.nova-canvas-v1:0');
+const model = amazonBedrock.image('amazon.nova-canvas-v1:0');
 ```
 
 You can then generate images with the `generateImage` function:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateImage } from 'ai';
 
 const { image } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: 'A beautiful sunset over a calm ocean',
   size: '512x512',
   seed: 42,
@@ -995,11 +1051,11 @@ const { image } = await generateImage({
 You can also pass the `providerOptions` object to the `generateImage` function to customize the generation behavior:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateImage } from 'ai';
 
 const { image } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: 'A beautiful sunset over a calm ocean',
   size: '512x512',
   seed: 42,
@@ -1052,7 +1108,7 @@ Create variations of an existing image while maintaining its core characteristic
 const imageBuffer = readFileSync('./input-image.png');
 
 const { images } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: {
     text: 'Modernize the style, photo-realistic, 8k, hdr',
     images: [imageBuffer],
@@ -1081,7 +1137,7 @@ Edit specific parts of an image. You can define the area to modify using either
 const imageBuffer = readFileSync('./input-image.png');
 
 const { images } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: {
     text: 'a cute corgi dog in the same style',
     images: [imageBuffer],
@@ -1102,7 +1158,7 @@ const image = readFileSync('./input-image.png');
 const mask = readFileSync('./mask.png'); // White pixels = area to change
 
 const { images } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: {
     text: 'A sunlit indoor lounge area with a pool containing a flamingo',
     images: [image],
@@ -1123,7 +1179,7 @@ Extend an image beyond its original boundaries:
 const imageBuffer = readFileSync('./input-image.png');
 
 const { images } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: {
     text: 'A beautiful sunset landscape with mountains',
     images: [imageBuffer],
@@ -1150,7 +1206,7 @@ Remove the background from an image:
 const imageBuffer = readFileSync('./input-image.png');
 
 const { images } = await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: {
     images: [imageBuffer],
   },
@@ -1193,7 +1249,7 @@ You can customize the generation behavior with optional options:
 
 ```ts
 await generateImage({
-  model: bedrock.image('amazon.nova-canvas-v1:0'),
+  model: amazonBedrock.image('amazon.nova-canvas-v1:0'),
   prompt: 'A beautiful sunset over a calm ocean',
   size: '512x512',
   seed: 42,
@@ -1228,11 +1284,11 @@ The Amazon Bedrock provider will return the response headers associated with
 network requests made of the Bedrock servers.
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { generateText } from 'ai';
 
 const { text } = await generateText({
-  model: bedrock('meta.llama3-70b-instruct-v1:0'),
+  model: amazonBedrock('meta.llama3-70b-instruct-v1:0'),
   prompt: 'Write a vegetarian lasagna recipe for 4 people.',
 });
 
@@ -1255,11 +1311,11 @@ be useful for correlating Bedrock API calls with requests made by the AI SDK:
 This information is also available with `streamText`:
 
 ```ts
-import { bedrock } from '@ai-sdk/amazon-bedrock';
+import { amazonBedrock } from '@ai-sdk/amazon-bedrock';
 import { streamText } from 'ai';
 
 const result = streamText({
-  model: bedrock('meta.llama3-70b-instruct-v1:0'),
+  model: amazonBedrock('meta.llama3-70b-instruct-v1:0'),
   prompt: 'Write a vegetarian lasagna recipe for 4 people.',
 });
 for await (const textPart of result.textStream) {
@@ -1328,8 +1384,10 @@ You can use the following optional settings to customize the Bedrock Anthropic p
 
 - **sessionToken** _string_
 
-  Optional. The AWS session token that you want to use for the API calls.
-  It uses the `AWS_SESSION_TOKEN` environment variable by default.
+  Optional. For temporary credentials. With **both** access keys set as strings,
+  pass the token here if needed; `AWS_SESSION_TOKEN` from the environment is not
+  used. If either key is taken from the environment, omitting `sessionToken`
+  allows `AWS_SESSION_TOKEN`.
 
 - **apiKey** _string_
 
@@ -1380,6 +1438,15 @@ const { text } = await generateText({
 });
 ```
 
+### Provider Options
+
+The following optional provider options are available for Bedrock Anthropic models:
+
+- `metadata` _object_
+
+  Optional. Metadata to include with the request. See the [Anthropic API documentation](https://platform.claude.com/docs/en/api/messages/create) for details.
+  - `userId` _string_ - An external identifier for the end-user.
+
 ### Cache Control
 
 In the messages and message parts, you can use the `providerOptions` property to set cache control breakpoints.
@@ -1433,7 +1500,7 @@ They are available via the `tools` property of the provider instance.
 
 ```ts
 import { bedrockAnthropic } from '@ai-sdk/amazon-bedrock/anthropic';
-import { generateText, stepCountIs } from 'ai';
+import { generateText, isStepCount } from 'ai';
 
 const result = await generateText({
   model: bedrockAnthropic('us.anthropic.claude-sonnet-4-5-20250929-v1:0'),
@@ -1446,7 +1513,7 @@ const result = await generateText({
     }),
   },
   prompt: 'List the files in my directory.',
-  stopWhen: stepCountIs(2),
+  stopWhen: isStepCount(2),
 });
 ```
 
@@ -1454,7 +1521,7 @@ const result = await generateText({
 
 ```ts
 import { bedrockAnthropic } from '@ai-sdk/amazon-bedrock/anthropic';
-import { generateText, stepCountIs } from 'ai';
+import { generateText, isStepCount } from 'ai';
 
 const result = await generateText({
   model: bedrockAnthropic('us.anthropic.claude-sonnet-4-5-20250929-v1:0'),
@@ -1467,7 +1534,7 @@ const result = await generateText({
     }),
   },
   prompt: 'Update my README file.',
-  stopWhen: stepCountIs(5),
+  stopWhen: isStepCount(5),
 });
 ```
 
@@ -1475,7 +1542,7 @@ const result = await generateText({
 
 ```ts
 import { bedrockAnthropic } from '@ai-sdk/amazon-bedrock/anthropic';
-import { generateText, stepCountIs } from 'ai';
+import { generateText, isStepCount } from 'ai';
 import fs from 'fs';
 
 const result = await generateText({
@@ -1510,7 +1577,7 @@ const result = await generateText({
     }),
   },
   prompt: 'Take a screenshot.',
-  stopWhen: stepCountIs(3),
+  stopWhen: isStepCount(3),
 });
 ```
 
@@ -1518,6 +1585,9 @@ const result = await generateText({
 
 Anthropic has reasoning support for Claude 3.7 and Claude 4 models on Bedrock, including:
 
+- `us.anthropic.claude-fable-5`
+- `us.anthropic.claude-opus-4-8`
+- `us.anthropic.claude-opus-4-7`
 - `us.anthropic.claude-opus-4-6-v1`
 - `us.anthropic.claude-opus-4-5-20251101-v1:0`
 - `us.anthropic.claude-sonnet-4-5-20250929-v1:0`
@@ -1554,6 +1624,9 @@ on how to integrate reasoning into your chatbot.
 
 | Model                                          | Image Input         | Object Generation   | Tool Usage          | Computer Use        | Reasoning           |
 | ---------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `us.anthropic.claude-fable-5`                  | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `us.anthropic.claude-opus-4-8`                 | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `us.anthropic.claude-opus-4-7`                 | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `us.anthropic.claude-opus-4-6-v1`              | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `us.anthropic.claude-opus-4-5-20251101-v1:0`   | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
 | `us.anthropic.claude-sonnet-4-5-20250929-v1:0` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
@@ -1569,6 +1642,163 @@ on how to integrate reasoning into your chatbot.
   Connector which are not supported on Bedrock.
 </Note>
 
+## Bedrock Mantle Provider Usage
+
+The Bedrock Mantle provider offers access to OpenAI-compatible models through Amazon Bedrock's Mantle API at `https://bedrock-mantle.{region}.api.aws/v1`. This endpoint supports the Chat Completions API and the Responses API, and provides access to models that may only be available through the Mantle endpoint (such as `openai.gpt-oss-120b`).
+
+### Provider Instance
+
+You can import the default provider instance `bedrockMantle` from `@ai-sdk/amazon-bedrock/mantle`:
+
+```typescript
+import { bedrockMantle } from '@ai-sdk/amazon-bedrock/mantle';
+```
+
+If you need a customized setup, you can import `createBedrockMantle` from `@ai-sdk/amazon-bedrock/mantle` and create a provider instance with your settings:
+
+```typescript
+import { createBedrockMantle } from '@ai-sdk/amazon-bedrock/mantle';
+
+const bedrockMantle = createBedrockMantle({
+  region: 'us-east-1', // optional
+  accessKeyId: 'xxxxxxxxx', // optional
+  secretAccessKey: 'xxxxxxxxx', // optional
+  sessionToken: 'xxxxxxxxx', // optional
+});
+```
+
+#### Provider Settings
+
+You can use the following optional settings to customize the Bedrock Mantle provider instance:
+
+- **region** _string_
+
+  The AWS region that you want to use for the API calls.
+  It uses the `AWS_REGION` environment variable by default.
+
+- **accessKeyId** _string_
+
+  The AWS access key ID that you want to use for the API calls.
+  It uses the `AWS_ACCESS_KEY_ID` environment variable by default.
+
+- **secretAccessKey** _string_
+
+  The AWS secret access key that you want to use for the API calls.
+  It uses the `AWS_SECRET_ACCESS_KEY` environment variable by default.
+
+- **sessionToken** _string_
+
+  Optional. The AWS session token that you want to use for the API calls.
+  It uses the `AWS_SESSION_TOKEN` environment variable by default.
+
+- **apiKey** _string_
+
+  API key for authenticating requests using Bearer token authentication.
+  When provided, this will be used instead of AWS SigV4 authentication.
+  It uses the `AWS_BEARER_TOKEN_BEDROCK` environment variable by default.
+
+- **baseURL** _string_
+
+  Base URL for the Bedrock Mantle API calls.
+  Defaults to `https://bedrock-mantle.{region}.api.aws/v1`.
+
+- **headers** _Record&lt;string, string | undefined&gt;_
+
+  Headers to include in the requests.
+
+- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_
+
+  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
+  You can use it as a middleware to intercept requests,
+  or to provide a custom fetch implementation for e.g. testing.
+
+- **credentialProvider** _() => PromiseLike&lt;BedrockCredentials&gt;_
+
+  The AWS credential provider to use for the Bedrock provider to get dynamic
+  credentials similar to the AWS SDK. Setting a provider here will cause its
+  credential values to be used instead of the `accessKeyId`, `secretAccessKey`,
+  and `sessionToken` settings.
+
+### Language Models
+
+You can create models using the Mantle provider instance. By default, the provider creates models using the Chat Completions API, which has the broadest model support on Mantle:
+
+```ts
+const model = bedrockMantle('openai.gpt-oss-120b');
+```
+
+You can also explicitly select the Chat Completions API or the Responses API:
+
+```ts
+const chatModel = bedrockMantle.chat('openai.gpt-oss-120b');
+const responsesModel = bedrockMantle.responses('openai.gpt-oss-120b');
+```
+
+Note that not all Mantle models support the Responses API. See the model capabilities table below.
+
+You can use Bedrock Mantle language models to generate text with the `generateText` function:
+
+```ts
+import { bedrockMantle } from '@ai-sdk/amazon-bedrock/mantle';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: bedrockMantle('openai.gpt-oss-120b'),
+  prompt: 'Invent a new holiday and describe its traditions.',
+});
+```
+
+Or stream text with the `streamText` function:
+
+```ts
+import { bedrockMantle } from '@ai-sdk/amazon-bedrock/mantle';
+import { streamText } from 'ai';
+
+const result = streamText({
+  model: bedrockMantle('openai.gpt-oss-120b'),
+  prompt: 'Invent a new holiday and describe its traditions.',
+});
+
+for await (const textPart of result.textStream) {
+  process.stdout.write(textPart);
+}
+```
+
+### Provider Options
+
+Since the Mantle API is OpenAI-compatible, provider options are passed under the `openai` namespace:
+
+```ts
+import { bedrockMantle } from '@ai-sdk/amazon-bedrock/mantle';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: bedrockMantle('openai.gpt-oss-120b'),
+  prompt: 'Hello!',
+  providerOptions: {
+    openai: {
+      // OpenAI-compatible provider options
+    },
+  },
+});
+```
+
+### Model Capabilities
+
+| Model                           | Chat Completions    | Responses API       |
+| ------------------------------- | ------------------- | ------------------- |
+| `openai.gpt-oss-20b`            | <Check size={18} /> | <Check size={18} /> |
+| `openai.gpt-oss-120b`           | <Check size={18} /> | <Check size={18} /> |
+| `openai.gpt-oss-safeguard-20b`  | <Check size={18} /> | <Cross size={18} /> |
+| `openai.gpt-oss-safeguard-120b` | <Check size={18} /> | <Cross size={18} /> |
+
+<Note>
+  The Bedrock Mantle provider uses the OpenAI-compatible API format. Models
+  available through the Mantle endpoint may differ from those available through
+  the Bedrock Converse API. Use the Mantle endpoint's model listing API to
+  discover all available models.
+</Note>
+
 ## Migrating to `@ai-sdk/amazon-bedrock` 2.x
 
 The Amazon Bedrock provider was rewritten in version 2.x to remove the
@@ -1578,8 +1808,4 @@ The `bedrockOptions` provider setting previously available has been removed. If
 you were using the `bedrockOptions` object, you should now use the `region`,
 `accessKeyId`, `secretAccessKey`, and `sessionToken` settings directly instead.
 
-Note that you may need to set all of these explicitly, e.g. even if you're not
-using `sessionToken`, set it to `undefined`. If you're running in a serverless
-environment, there may be default environment variables set by your containing
-environment that the Amazon Bedrock provider will then pick up and could
-conflict with the ones you're intending to use.
+Static IAM user keys do not require `sessionToken`.